generated from City-Bureau/city-scrapers-template
-
-
Notifications
You must be signed in to change notification settings - Fork 3
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Build: wicks_wampo_tabs mixin & 3 spiders
- Loading branch information
1 parent
a3f9911
commit 25f67f7
Showing
8 changed files
with
2,667 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,113 @@ | ||
import re | ||
from datetime import datetime | ||
|
||
from city_scrapers_core.constants import COMMITTEE | ||
from city_scrapers_core.items import Meeting | ||
from city_scrapers_core.spiders import CityScrapersSpider | ||
from dateutil.parser import parse | ||
|
||
|
||
class WampoMixinTabsMeta(type): | ||
""" | ||
Metaclass that enforces the implementation of required static | ||
variables in child classes that inherit from WampoMixinTabs. | ||
""" | ||
|
||
def __init__(cls, name, bases, dct): | ||
required_static_vars = [ | ||
"name", | ||
"agency", | ||
"start_urls", | ||
"start_time", | ||
] | ||
missing_vars = [var for var in required_static_vars if var not in dct] | ||
|
||
if missing_vars: | ||
missing_vars_str = ", ".join(missing_vars) | ||
raise NotImplementedError( | ||
f"{name} must define the following static variable(s): {missing_vars_str}." # noqa | ||
) | ||
|
||
super().__init__(name, bases, dct) | ||
|
||
|
||
class WampoMixinTabs(CityScrapersSpider, metaclass=WampoMixinTabsMeta): | ||
""" | ||
This mixin is designed for scraping meeting data from specific pages on the | ||
website of the Wichita Area Metropolitan Planning Organization (WAMPO) that use | ||
a tabbed interface. It is not applicable for all WAMPO pages. | ||
Child classes must define 'name', 'agency', 'start_urls', 'start_time', and 'location' # noqa | ||
as static variables. | ||
""" | ||
|
||
name = None | ||
agency = None | ||
start_urls = None | ||
location = { | ||
"name": "Wichita Area Metropolitan Planning Organization", | ||
"address": "271 W. 3rd St. N., Suite 101, Wichita, KS 67202", | ||
} | ||
timezone = "America/Chicago" | ||
start_time = None | ||
|
||
def parse(self, response): | ||
""" | ||
Parse the page and extract the meeting information. | ||
""" | ||
for item in response.css("div[role='tabpanel'] ul li p"): | ||
start = self._parse_start(item) | ||
if start is None: | ||
self.logger.warn("Skipping row with no date") | ||
continue | ||
meeting = Meeting( | ||
title="Executive Committee Meeting", | ||
description="", | ||
classification=COMMITTEE, | ||
start=start, | ||
end=None, | ||
all_day=False, | ||
time_notes="", | ||
location=self.location, | ||
links=self._parse_links(item), | ||
source=response.url, | ||
) | ||
meeting["status"] = self._get_status(meeting) | ||
meeting["id"] = self._get_id(meeting) | ||
yield meeting | ||
|
||
def _parse_start(self, item): | ||
""" | ||
Extracts all the text from the row and parses the first | ||
column that looks formatted like 11/1/2024 or November 12, 2024. | ||
""" | ||
item.css("span::text").extract() | ||
for text in item.css("span::text").extract(): | ||
clean_text = text.strip() | ||
if re.match( | ||
r"(?:[a-zA-Z]+\s\d{1,2},\s\d{4})|(?:\d{1,2}\/\d{1,2}\/\d{2,4})", | ||
clean_text, | ||
): | ||
try: | ||
start_date = parse(clean_text) | ||
start_datetime = datetime.combine(start_date, self.start_time) | ||
return start_datetime | ||
except ValueError: | ||
self.logger.info(f"Could not parse date from {clean_text}") | ||
return None | ||
self.logger.info("Could not find date in row") | ||
return None | ||
|
||
def _parse_links(self, item): | ||
""" | ||
Parse all links in the row. | ||
""" | ||
links = [] | ||
for link in item.css("a"): | ||
links.append( | ||
{ | ||
"href": link.attrib["href"], | ||
"title": link.css("::text").extract_first(), | ||
} | ||
) | ||
return links |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,73 @@ | ||
import re | ||
from datetime import datetime, time | ||
|
||
from city_scrapers_core.constants import COMMITTEE | ||
from city_scrapers_core.items import Meeting | ||
from city_scrapers_core.spiders import CityScrapersSpider | ||
|
||
|
||
class WampoEcSpider(CityScrapersSpider): | ||
name = "wicks_wampo_ec" | ||
agency = "Wichita Area Metropolitan Planning Organization – Executive Committee" | ||
timezone = "America/Chicago" | ||
start_urls = ["https://www.wampo.org/executive-committee"] | ||
start_time = time(11, 0) | ||
location = { | ||
"name": "Wichita Area Metropolitan Planning Organization", | ||
"address": "271 W. 3rd St. N., Suite 101, Wichita, KS 67202", | ||
} | ||
|
||
def parse(self, response): | ||
""" | ||
Parse the page and extract the meeting information. | ||
""" | ||
for tabpanel in response.css("div[role='tabpanel'] ul"): | ||
for item in tabpanel.css("li p"): | ||
start = self._parse_start(item) | ||
if start is None: | ||
self.logger.warn("Skipping row with no date") | ||
continue | ||
meeting = Meeting( | ||
title="Executive Committee Meeting", | ||
description="", | ||
classification=COMMITTEE, | ||
start=start, | ||
end=None, | ||
all_day=False, | ||
time_notes="", | ||
location=self.location, | ||
links=self._parse_links(item), | ||
source=response.url, | ||
) | ||
meeting["status"] = self._get_status(meeting) | ||
meeting["id"] = self._get_id(meeting) | ||
yield meeting | ||
|
||
def _parse_start(self, item): | ||
"""Extracts all the text from the row and parses the first | ||
column that looks formatted like MM/DD/YYYY.""" | ||
item.css("span::text").extract() | ||
for text in item.css("span::text").extract(): | ||
clean_text = text.strip() | ||
if re.match(r"\d{1,2}/\d{1,2}/\d{4}", clean_text): | ||
try: | ||
start_date = datetime.strptime(clean_text, "%m/%d/%Y") | ||
start_datetime = datetime.combine(start_date, self.start_time) | ||
return start_datetime | ||
except ValueError: | ||
self.logger.info(f"Could not parse date from {clean_text}") | ||
return None | ||
self.logger.info("Could not find date in row") | ||
return None | ||
|
||
def _parse_links(self, item): | ||
"""Parse all links in the row.""" | ||
links = [] | ||
for link in item.css("a"): | ||
links.append( | ||
{ | ||
"href": link.attrib["href"], | ||
"title": link.css("::text").extract_first(), | ||
} | ||
) | ||
return links |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,54 @@ | ||
from datetime import time | ||
|
||
from city_scrapers_core.constants import COMMITTEE | ||
|
||
from city_scrapers.mixins.wampo_tabs import WampoMixinTabs | ||
|
||
# Configuration for each spider | ||
spider_configs = [ | ||
{ | ||
"class_name": "WampoECSpider", | ||
"name": "wicks_wampo_ec", | ||
"agency": "Wichita Area Metropolitan Planning Organization – Executive Committee", # noqa | ||
"start_urls": ["https://www.wampo.org/executive-committee"], | ||
"start_time": time(11, 0), | ||
"classification": COMMITTEE, | ||
}, | ||
{ | ||
"class_name": "WicksWampoICTSSpider", | ||
"name": "wicks_wampo_icts", | ||
"agency": "Wichita Area Metropolitan Planning Organization – ICT Safe", | ||
"start_urls": ["https://www.wampo.org/ict-safe"], | ||
"start_time": time(9, 30), | ||
"classification": COMMITTEE, | ||
}, | ||
{ | ||
"class_name": "WicksWampoUCTCSpider", | ||
"name": "wicks_wampo_uctc", | ||
"agency": "Wichita Area Metropolitan Planning Organization – United Community Transit Coalition", # noqa | ||
"start_urls": ["https://www.wampo.org/uctc"], | ||
"start_time": time(14, 0), | ||
"classification": COMMITTEE, | ||
}, | ||
] | ||
|
||
|
||
def create_spiders(): | ||
""" | ||
Dynamically create spider classes using the spider_configs list | ||
and then register them in the global namespace. This approach | ||
is the equivalent of declaring each spider class in the same | ||
file but it is more concise and centralized. | ||
""" | ||
for config in spider_configs: | ||
class_name = config.pop("class_name") | ||
if class_name not in globals(): | ||
spider_class = type( | ||
class_name, | ||
(WampoMixinTabs,), # Base class | ||
{**config}, # Attributes | ||
) | ||
globals()[class_name] = spider_class | ||
|
||
|
||
create_spiders() |
Oops, something went wrong.